In [1]:
from PIL import Image
from statistics import *
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
In [2]:
import cse351_hw1_zhang_junhui_112895310
In [3]:
airbnb_data = pd.read_csv("AB_NYC_2019.csv")
In [4]:
# Question 1
removedAnomaly = cse351_hw1_zhang_junhui_112895310.removeAnomaly(airbnb_data);
In [5]:
removedAnomaly
Out[5]:
id name host_id host_name neighbourhood_group neighbourhood latitude longitude room_type price minimum_nights number_of_reviews last_review reviews_per_month calculated_host_listings_count availability_365
0 2539 Clean & quiet apt home by the park 2787 John Brooklyn Kensington 40.64749 -73.97237 Private room 149 1 9 10/19/2018 0.21 6 365
1 2595 Skylit Midtown Castle 2845 Jennifer Manhattan Midtown 40.75362 -73.98377 Entire home/apt 225 1 45 5/21/2019 0.38 2 355
2 3647 THE VILLAGE OF HARLEM....NEW YORK ! 4632 Elisabeth Manhattan Harlem 40.80902 -73.94190 Private room 150 3 0 NaN NaN 1 365
3 3831 Cozy Entire Floor of Brownstone 4869 LisaRoxanne Brooklyn Clinton Hill 40.68514 -73.95976 Entire home/apt 89 1 270 7/5/2019 4.64 1 194
5 5099 Large Cozy 1 BR Apartment In Midtown East 7322 Chris Manhattan Murray Hill 40.74767 -73.97500 Entire home/apt 200 3 74 6/22/2019 0.59 1 129
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
48890 36484665 Charming one bedroom - newly renovated rowhouse 8232441 Sabrina Brooklyn Bedford-Stuyvesant 40.67853 -73.94995 Private room 70 2 0 NaN NaN 2 9
48891 36485057 Affordable room in Bushwick/East Williamsburg 6570630 Marisol Brooklyn Bushwick 40.70184 -73.93317 Private room 40 4 0 NaN NaN 2 36
48892 36485431 Sunny Studio at Historical Neighborhood 23492952 Ilgar & Aysel Manhattan Harlem 40.81475 -73.94867 Entire home/apt 115 10 0 NaN NaN 1 27
48893 36485609 43rd St. Time Square-cozy single bed 30985759 Taz Manhattan Hell's Kitchen 40.75751 -73.99112 Shared room 55 1 0 NaN NaN 6 2
48894 36487245 Trendy duplex in the very heart of Hell's Kitchen 68119814 Christophe Manhattan Hell's Kitchen 40.76404 -73.98933 Private room 90 7 0 NaN NaN 1 23

31103 rows × 16 columns

In [6]:
# Question 2A
top5bot5List = cse351_hw1_zhang_junhui_112895310.getTop5Bot5Price(removedAnomaly)
In [7]:
top5bot5List
Out[7]:
{'Top5': ['Riverdale', 'Tribeca', 'Flatiron District', 'NoHo', 'SoHo'],
 'Bot5': ['Schuylerville',
  'Hunts Point',
  'New Brighton',
  'Soundview',
  'Far Rockaway']}
In [8]:
# Question 2B
cse351_hw1_zhang_junhui_112895310.plotTop5Bot5(top5bot5List, removedAnomaly)
In [9]:
# Question 3
cse351_hw1_zhang_junhui_112895310.createCorrelationHeatMap(removedAnomaly)
In [10]:
# Question 4A
cse351_hw1_zhang_junhui_112895310.plotByBorough(removedAnomaly)
In [11]:
# Question 4B
cse351_hw1_zhang_junhui_112895310.generatePlotByPrice(removedAnomaly)
In [12]:
# Question 5
cse351_hw1_zhang_junhui_112895310.generateWordCloud(removedAnomaly)
In [13]:
# Question 6
cse351_hw1_zhang_junhui_112895310.generatePlotByListings(removedAnomaly)
In [14]:
cse351_hw1_zhang_junhui_112895310.generatePlotByAvailability(removedAnomaly)
In [15]:
cse351_hw1_zhang_junhui_112895310.generatePlotByPrice(removedAnomaly)
In [16]:
cse351_hw1_zhang_junhui_112895310.generatePlotByReviews(removedAnomaly)
In [ ]:
In [ ]:
In [ ]:
In [17]:
# Question 7
cse351_hw1_zhang_junhui_112895310.generatePlotByRoomType(airbnb_data)
In [18]:
cse351_hw1_zhang_junhui_112895310.generatePlotByPrice(removedAnomaly)
In [19]:
# Explainations in py file
In [ ]: